[BugFix] fix some typos found by typos. (#16314)

Signed-off-by: yihong0618 <zouzou0208@gmail.com>
This commit is contained in:
yihong
2025-04-09 03:43:59 -07:00
committed by GitHub
parent 24834f4894
commit 04149cce27
21 changed files with 33 additions and 33 deletions
+1 -1
View File
@@ -446,7 +446,7 @@ def flash_paged_attention(
IO tensor dtypes:
- This kernel assumes all IO tensors have the same dtype except for
block_tables (int32) and mask (int32)
- If mixed_percision is True, then all Tensor Engine operation will be
- If mixed_precision is True, then all Tensor Engine operation will be
performed in bfloat16 and accumulation will be performed in float32.
Otherwise the intermediates will be in the same type as the inputs.